Multi-Level Quickening: Ten Years Later

Abstract

This paper presents important performance improvements for interpreters, exemplified by speedups of up to 5.5$\times$ for CPython. Although the original version of this papers was rejected multiple times, the reported speedups have not been achieved by any other interpreter optimization technique since. In addition, the paper uses a sound evaluation methodology based on a corollary on Amdahl's law to quantify the speedup potential of benchmarks, which also has not been used in any other paper since. This paper documents my best efforts, and includes all of the reviews the paper received, plus some more commentary on my side on what has changed since and what purpose the archived document could serve.